🛠 Tech Stack

💼 About This Role

You'll design and scale machine learning algorithms for LLM post-training, focusing on distributed RL methods. You'll enhance the post-training codebase with new tools and optimizations, scaling RL to unprecedented levels. This role offers the chance to work across engineering and research teams at a leading AI company.

🎯 What You'll Do

• Design and write high-performing scalable software for training models.
• Develop new tools to support and accelerate research and LLM training.
• Coordinate with engineering and scientific teams for integrated post-training.
• Implement techniques to improve performance and speed up training cycles.

📋 Requirements

• Extremely strong software engineering skills.
• Value test-driven development and clean code.
• Proficiency in Python and related ML frameworks (JAX, PyTorch, XLA/MLIR).
• Experience with large-scale distributed training strategies.

✨ Nice to Have

• Experience with distributed training infrastructures (Kubernetes, Ray).
• Hands-on experience with post-training phase of model training.
• Experience in ML, LLM and RL academic research.

🎁 Benefits & Perks

• 🤝 Open and inclusive culture
• 🍽 Weekly lunch stipend and in-office lunches
• 🦷 Full health and dental benefits including mental health budget
• 🐣 100% Parental Leave top-up up to 6 months
• ✈️ 6 weeks of vacation (30 working days)